© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2630
    Prev
    Next
    INDEX
    Explanations

    phrases or structures indicating a list of two or more items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "two" or number words

    np_acts-logits-general · gemini-2.0-flash

    two followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     étrangers
    -0.39
     all
    -0.39
     variés
    -0.38
     kaikk
    -0.38
     variously
    -0.38
     múltiple
    -0.37
    TargetException
    -0.36
     TextAppearance
    -0.36
     various
    -0.35
     ویکی‌پدیای
    -0.34
    POSITIVE LOGITS
     two
    1.04
    two
    1.00
    Two
    0.96
     deux
    0.95
     zwei
    0.92
     beiden
    0.90
     Two
    0.89
    兩個
    0.83
     TWO
    0.82
    两个
    0.82
    Activations Density 1.843%

    No Known Activations